Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Jan 30:11:1109236.
doi: 10.3389/fpubh.2023.1109236. eCollection 2023.

A framework to distinguish healthy/cancer renal CT images using the fused deep features

Venkatesan Rajinikanth  1 , P M Durai Raj Vincent  2 , Kathiravan Srinivasan  3 , G Ananth Prabhu  4 , Chuan-Yu Chang  5   6
Affiliations

A framework to distinguish healthy/cancer renal CT images using the fused deep features

Venkatesan Rajinikanth et al. Front Public Health. .

Abstract

Introduction: Cancer happening rates in humankind are gradually rising due to a variety of reasons, and sensible detection and management are essential to decrease the disease rates. The kidney is one of the vital organs in human physiology, and cancer in the kidney is a medical emergency and needs accurate diagnosis and well-organized management.

Methods: The proposed work aims to develop a framework to classify renal computed tomography (CT) images into healthy/cancer classes using pre-trained deep-learning schemes. To improve the detection accuracy, this work suggests a threshold filter-based pre-processing scheme, which helps in removing the artefact in the CT slices to achieve better detection. The various stages of this scheme involve: (i) Image collection, resizing, and artefact removal, (ii) Deep features extraction, (iii) Feature reduction and fusion, and (iv) Binary classification using five-fold cross-validation.

Results and discussion: This experimental investigation is executed separately for: (i) CT slices with the artefact and (ii) CT slices without the artefact. As a result of the experimental outcome of this study, the K-Nearest Neighbor (KNN) classifier is able to achieve 100% detection accuracy by using the pre-processed CT slices. Therefore, this scheme can be considered for the purpose of examining clinical grade renal CT images, as it is clinically significant.

Keywords: KNN classifier; deep learning; kidney cancer; renal CT slices; validation.

PubMed Disclaimer

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
Kidney cancer detection framework.
Figure 2
Figure 2
Sample axial-plane test images of renal CT slices.
Figure 3
Figure 3
Implementation of threshold filter to eliminate the artifact. (A) Original image. (B) Processed image. (C) Artifact. (D) Gray-scale histogram.
Figure 4
Figure 4
Integrated Glyph plot to demonstrate the overall performance of the considered methods.
Figure 5
Figure 5
Convergence of training and validation process. (A) Accuracy. (B) Loss.
Figure 6
Figure 6
Intermediate layer outcomes collected from VGG19. (A) Conv1. (B) Conv2. (C) Conv3. (D) Conv4. (E) Conv5.
Figure 7
Figure 7
Confusion matrix and ROC curve achieved with fused features. (A) Confusion matrix. (B) the ROC curve.
Figure 8
Figure 8
Spider plot achieved using the results of Table 6. (A) VGG19. (B) DenseNet121. (C) Fused deep features (VGG+DN).
See this image and copyright information in PMC

References

    1. Amin J, Sharif M, Fernandes SL, Wang SH, Saba T, Khan AR. Breast microscopic cancer segmentation and classification using unique 4-qubit-quantum model. Microsc Res Tech. (2022) 85:1926–36. 10.1002/jemt.24054 - DOI - PubMed
    1. Fernandes SL, Martis RJ, Lin H, Javadi B, Tanik UJ, Sharif M. Recent advances in deep learning, biometrics, health informatics, and data science. Expert Systems. (2022) 39:e13060. 10.1111/exsy.13060 - DOI
    1. Wang SH, Fernandes SL, Zhu Z, Zhang YD, AVNC. attention-based VGG-style network for COVID-19 diagnosis by CBAM. IEEE Sens J. (2021) 22:17431–8. 10.1109/JSEN.2021.3062442 - DOI - PMC - PubMed
    1. Ueda T. Estimation of three-dimensional particle size and shape characteristics using a modified 2D−3D conversion method employing spherical harmonic-based principal component analysis. Powder Technol. (2022) 404:117461. 10.1016/j.powtec.2022.117461 - DOI
    1. Krishnamoorthy S, Zhang Y, Kadry S, Yu W. Framework to segment and evaluate multiple sclerosis lesion in MRI slices using VGG-UNet. Comput Intell Neurosci. (2022) 2022:8096. 10.1155/2022/4928096 - DOI - PMC - PubMed

Publication types